Publication:
Transformer-Based Model for Malicious URL Classification

Simple item page
dc.citedby1
dc.contributor.authorDo N.Q.en_US
dc.contributor.authorSelamat A.en_US
dc.contributor.authorLim K.C.en_US
dc.contributor.authorKrejcar O.en_US
dc.contributor.authorGhani N.A.M.en_US
dc.contributor.authorid57283917100en_US
dc.contributor.authorid24468984100en_US
dc.contributor.authorid57889660500en_US
dc.contributor.authorid14719632500en_US
dc.contributor.authorid57215593148en_US
dc.date.accessioned2024-10-14T03:19:24Z
dc.date.available2024-10-14T03:19:24Z
dc.date.issued2023
dc.description.abstractIn recent years, cyber threats including malicious software, virus, spam, and phishing have grown aggressively via compromised Uniform Resource Locators (URLs). However, the current phishing URL detection solutions based on supervised learning use labeled data for training and classification, leading to the dependency on known attacking patterns. These approaches have limitations in fighting against evolving phishing tactics, resulting in a lack of robustness and sustainability. In this study, an unsupervised transformer model is proposed to address the drawbacks of the existing methods which use supervised learning to combat zero-day phishing attacks. Specifically, Bidirectional Encoder Representations from Transformers (BERT) is adopted in this paper to classify malicious URLs. The proposed model was trained on a public dataset and benchmarked with various baseline models using several performance metrics. Results obtained from the experiments showed that BERT-Medium achieved the highest detection accuracy of 98.55% among numerous transformer based models and outperformed other text embedding and deep learning techniques, indicating that the proposed solution is effective and robust in detecting phishing URLs. � 2023 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1109/ICOCO59262.2023.10397705
dc.identifier.epage327
dc.identifier.scopus2-s2.0-85184851119
dc.identifier.spage323
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85184851119&doi=10.1109%2fICOCO59262.2023.10397705&partnerID=40&md5=e95b171838ae85d7e157717e8b8fd6f6
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/34380
dc.pagecount4
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitle2023 IEEE International Conference on Computing, ICOCO 2023
dc.subjectmalicious URL classification
dc.subjectnatural language processing
dc.subjectphishing detection
dc.subjecttransformer model
dc.subjectunsupervised learning
dc.subjectClassification (of information)
dc.subjectComputer crime
dc.subjectLearning algorithms
dc.subjectLearning systems
dc.subjectNatural language processing systems
dc.subjectSupervised learning
dc.subjectViruses
dc.subjectZero-day attack
dc.subject'current
dc.subjectCyber threats
dc.subjectLabeled data
dc.subjectLanguage processing
dc.subjectMalicious uniform resource locator classification
dc.subjectNatural language processing
dc.subjectNatural languages
dc.subjectPhishing
dc.subjectPhishing detections
dc.subjectTransformer modeling
dc.subjectDeep learning
dc.titleTransformer-Based Model for Malicious URL Classificationen_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS